169 citations · 528 across the 23 of their papers we have counts for
16 papers · 1 filter
Masked Autoregressive Speech Enhancement with Continuous Neural Audio Codec Representations
Yoto Fujita, Simon Leglaive, Laurent Girin
Most previous work on speech enhancement (SE) based on masked generative modeling relied on discrete token representations of audio signals, obtained using neural audio codecs (NAC…
Test-time adaptation for speech enhancement with an autoregressive speech prior
Sofiene Kammoun, Simon Leglaive, Xavier Alameda-Pineda +1
Test-time adaptation (TTA) offers a promising direction for improving speech enhancement models under mismatched acoustic conditions, without requiring access to labeled target dat…
Modeling strategies for speech enhancement in the latent space of a neural audio codec
Sofiene Kammoun, Xavier Alameda-Pineda, Simon Leglaive
Neural audio codecs (NACs) provide compact latent speech representations in the form of sequences of continuous vectors or discrete tokens. In this work, we investigate how these t…
AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder
Samir Sadok, Simon Leglaive, Laurent Girin +2
This article introduces AnCoGen, a novel method that leverages a masked autoencoder to unify the analysis, control, and generation of speech signals within a single model. AnCoGen…
Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge
Simon Leglaive, Matthieu Fraticelli, Hend ElGhazaly +7
Supervised models for speech enhancement are trained using artificially generated mixtures of clean speech and noise signals. However, the synthetic training conditions may not acc…
The CHiME-7 UDASE task: Unsupervised domain adaptation for conversational speech enhancement
Simon Leglaive, Léonie Borne, Efthymios Tzinis +6
Supervised speech enhancement models are trained using artificially generated mixtures of clean speech and noise signals, which may not match real-world recording conditions at tes…
A multimodal dynamical variational autoencoder for audiovisual speech representation learning
Samir Sadok, Simon Leglaive, Laurent Girin +2
In this paper, we present a multimodal and dynamical VAE (MDVAE) applied to unsupervised audio-visual speech representation learning. The latent space is structured to dissociate t…
A vector quantized masked autoencoder for audiovisual speech emotion recognition
Samir Sadok, Simon Leglaive, Renaud Séguier
An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised mult…
A vector quantized masked autoencoder for speech emotion recognition
Samir Sadok, Simon Leglaive, Renaud Séguier
Recent years have seen remarkable progress in speech emotion recognition (SER), thanks to advances in deep learning techniques. However, the limited availability of labeled data re…
Learning and controlling the source-filter representation of speech with a variational autoencoder
Samir Sadok, Simon Leglaive, Laurent Girin +2
Understanding and controlling latent representations in deep generative models is a challenging yet important problem for analyzing, transforming and generating various types of da…
A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling
Xiaoyu Bie, Laurent Girin, Simon Leglaive +2
The Variational Autoencoder (VAE) is a powerful deep generative model that is now extensively used to represent high-dimensional complex data via a low-dimensional latent space lea…
Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders
Xiaoyu Bie, Simon Leglaive, Xavier Alameda-Pineda +1
Dynamical variational autoencoders (DVAEs) are a class of deep generative models with latent variables, dedicated to model time series of high-dimensional data. DVAEs can be consid…
Audio-visual Speech Enhancement Using Conditional Variational Auto-Encoders
Mostafa Sadeghi, Simon Leglaive, Xavier Alameda-PIneda +2
Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to lear…
Speech enhancement with variational autoencoders and alpha-stable distributions
Simon Leglaive, Umut Simsekli, Antoine Liutkus +2
This paper focuses on single-channel semi-supervised speech enhancement. We learn a speaker-independent deep generative speech model using the framework of variational autoencoders…
A variance modeling framework based on variational autoencoders for speech enhancement
Simon Leglaive, Laurent Girin, Radu Horaud
In this paper we address the problem of enhancing speech signals in noisy mixtures using a source separation approach. We explore the use of neural networks as an alternative to a…
Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization
Simon Leglaive, Laurent Girin, Radu Horaud
In this paper we address speaker-independent multichannel speech enhancement in unknown noisy environments. Our work is based on a well-established multichannel local Gaussian mode…